Nathan Lambert

from openai import OpenAI

# initialize the client but point it to TGI
client = OpenAI(
    base_url="<ENDPOINT_URL>" + "/v1/",  # replace with your endpoint url
    api_key="<HF_API_TOKEN>",  # replace with your token
)
chat_completion = client.chat.completions.create(
    model="tgi",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Why is open-source software important?"},
    ],
    stream=True,
    max_tokens=500
)

# iterate and print stream
for message in chat_completion:
    print(message.choices[0].delta.content, end="")